Borrowing it
Nothing to install: this file belongs to fmind/agent-supagents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fmind/agent-supagents/main/AGENTS.mdgit clone --depth 1 https://github.com/fmind/agent-supagentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/fmind/agent-supagents/agents-md)<a href="https://agentmods.dev/instructions/fmind/agent-supagents/agents-md"><img src="https://agentmods.dev/badge/instructions/fmind/agent-supagents/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/fmind/agent-supagents/agents-md"><img src="https://agentmods.dev/badge/instructions/fmind/agent-supagents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00860 | $0.00860 |
| Opus 5.5 | $0.00344 | $0.00344 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
agent-supagents AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
- agent-supagents is a Python CLI (
supagents) that compiles one markdown source into per-target subagent files for Antigravity, Claude Code, Codex, Gemini CLI, GitHub Copilot, Grok, Cursor, OpenCode, and Kilo Code. - The repo also ships harness manifests (
.claude-plugin/,gemini-extension.json,plugin.json) and an Agent Skill underskills/use-agent-supagents/so the same tree installs as a plugin in Claude Code, Gemini CLI, and GitHub Copilot. - Python ≥ 3.12. Tight dependency surface:
typer,rich,ruamel.yaml,pydantic,tomli-w. No I/O outside the documented source/output paths.
Conventions
- Stack & tooling. uv for env/lock; ruff (
format+check) for style;tyfor types;pytest(+pytest-cov, ≥90% gate) for tests.miseowns pinned tools and tasks. - Local checks.
mise run all(format, check, audit, test, build and isolated wheel smoke test) mirrors CI. Run it before delivery. - Hooks. Lefthook runs
checkbefore commit andtestbefore push (seelefthook.yml). Don't bypass with--no-verify— fix the underlying issue. - Skill files. Skill bodies (
skills/*/SKILL.md) load into agent context on every run; verbosity costs budget. Aim for ≤ 110 lines perSKILL.md. Use the imperative ("Read X, then write Y") and avoid second-person flavor text aimed at the human reader — that belongs in the README.
Workflow
- For non-trivial changes, work on a feature branch and open a PR. Keep diffs focused: source-only changes shouldn't touch generated outputs from other repos.
- When changing
src/supagents/, rerunmise run checkandmise run test— the test suite covers parsing, planning, and idempotent writes. - When changing
skills/use-agent-supagents/SKILL.md, re-read the whole file end-to-end after the edit — agents load it as a unit, so coherence matters more than line-level diffs.
Layout
src/supagents/— Python package:cli.py(Typer entry points),config.py(targets, scopes),core.py(parse/plan/write),__main__.py(python -m supagents).tests/—pytestsuite with fixtures undertests/fixtures/;conftest.pyholds shared scaffolding.skills/use-agent-supagents/SKILL.md— user-facing Agent Skill: how to author sources, run the CLI, gate CI..claude-plugin/— Claude Code plugin manifest (plugin.json) and bundled marketplace (marketplace.json).gemini-extension.json— Gemini CLI extension manifest.plugin.json— GitHub Copilot plugin manifest..pre-commit-hooks.yaml— exposes thesupagents-buildhook so downstream repos canrepo: https://github.com/fmind/agent-supagentsit..github/workflows/{ci,cd}.yml— CI (lint + test on push/PR) and CD (qualified artifacts published after a GitHub release).mise.toml/mise.lock— tools and canonical tasks;lefthook.yml— local hooks.docs/usage.md— source format, native target references, configuration, and migration contracts.docs/compatibility.md— versioned compiler/discovery evidence and runtime verification limits; refresh withmise run check:hostswhen native profiles change.examples/reviewer.md— portable reviewer source;scripts/check_hosts.pyprobes synthetic profile discovery without model calls or writes to installed profiles.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +3 lines · +87 tokens per session 6a23ea04ed18
- 1mo ago First seen · 33 lines · 773 tokens per session scan A 9888d698c098
agent-supagents AGENTS.md is an instructions file published in the GitHub repository fmind/agent-supagents (6 stars, last pushed yesterday), licensed MIT. It adds 860 tokens to every session, about $0.0034 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.